Precision: [tensor(0.7015, device='cuda:0'), tensor(0.7057, device='cuda:0'), tensor(0.7054, device='cuda:0'), tensor(0.7015, device='cuda:0'), tensor(0.7018, device='cuda:0'), tensor(0.7046, device='cuda:0'), tensor(0.7120, device='cuda:0'), tensor(0.7107, device='cuda:0'), tensor(0.6997, device='cuda:0'), tensor(0.7012, device='cuda:0')]
Output distance: [tensor(4.9031, device='cuda:0'), tensor(4.8947, device='cuda:0'), tensor(4.8952, device='cuda:0'), tensor(4.9031, device='cuda:0'), tensor(4.9026, device='cuda:0'), tensor(4.8968, device='cuda:0'), tensor(4.8821, device='cuda:0'), tensor(4.8847, device='cuda:0'), tensor(4.9068, device='cuda:0'), tensor(4.9036, device='cuda:0')]
Prediction loss: [tensor(37.0869, device='cuda:0'), tensor(34.8057, device='cuda:0'), tensor(37.3564, device='cuda:0'), tensor(36.0392, device='cuda:0'), tensor(36.1099, device='cuda:0'), tensor(35.6413, device='cuda:0'), tensor(36.6494, device='cuda:0'), tensor(36.5525, device='cuda:0'), tensor(35.0264, device='cuda:0'), tensor(36.3196, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]
Compressed training loss: [tensor(48703.0391, device='cuda:0'), tensor(48715.1758, device='cuda:0'), tensor(48746.2617, device='cuda:0'), tensor(48708.9883, device='cuda:0'), tensor(48913.9062, device='cuda:0'), tensor(48815.9141, device='cuda:0'), tensor(48806.0820, device='cuda:0'), tensor(48949.0625, device='cuda:0'), tensor(48888.2305, device='cuda:0'), tensor(48776.0195, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=1, microseconds=322184), datetime.timedelta(seconds=1, microseconds=202897), datetime.timedelta(seconds=1, microseconds=49547), datetime.timedelta(seconds=1, microseconds=200852), datetime.timedelta(seconds=1, microseconds=44571), datetime.timedelta(seconds=1, microseconds=43571), datetime.timedelta(seconds=1, microseconds=194932), datetime.timedelta(seconds=1, microseconds=53478), datetime.timedelta(seconds=1, microseconds=53563), datetime.timedelta(seconds=1, microseconds=214845)]
Phi time: [datetime.timedelta(seconds=5, microseconds=668947), datetime.timedelta(seconds=5, microseconds=671936), datetime.timedelta(seconds=5, microseconds=669945), datetime.timedelta(seconds=5, microseconds=669943), datetime.timedelta(seconds=5, microseconds=675965), datetime.timedelta(seconds=5, microseconds=672930), datetime.timedelta(seconds=5, microseconds=692841), datetime.timedelta(seconds=5, microseconds=674924), datetime.timedelta(seconds=5, microseconds=692896), datetime.timedelta(seconds=5, microseconds=668948)]
